COMPARISON BETWEEN DEEP NEURAL NETWORK AND PRINCIPAL COMPONENT ANALYSIS ALGORITHM IN FACE RECOGNITION

ANGELLA, NADYA (2022) COMPARISON BETWEEN DEEP NEURAL NETWORK AND PRINCIPAL COMPONENT ANALYSIS ALGORITHM IN FACE RECOGNITION. Other thesis, Universitas Katholik Soegijapranata Semarang.

Preview	Text 18.K1.0008-NADYA ANGELLA_COVER_a.pdf Download (2MB) | Preview
Preview	Text 18.K1.0008-NADYA ANGELLA_BAB I_a.pdf Download (1MB) | Preview
	Text 18.K1.0008-NADYA ANGELLA_BAB II_a.pdf Restricted to Registered users only Download (1MB)
Preview	Text 18.K1.0008-NADYA ANGELLA_BAB III_a.pdf Download (1MB) | Preview
Preview	Text 18.K1.0008-NADYA ANGELLA_BAB IV_a.pdf Download (1MB) | Preview
Preview	Text 18.K1.0008-NADYA ANGELLA_BAB V_a.pdf Download (1MB) | Preview
Preview	Text 18.K1.0008-NADYA ANGELLA_BAB VI_a.pdf Download (1MB) | Preview
Preview	Text 18.K1.0008-NADYA ANGELLA_DAPUS_a.pdf Download (1MB) | Preview
Preview	Text 18.K1.0008-NADYA ANGELLA_LAMP_a.pdf Download (1MB) | Preview

Abstract

Face recognition is one technology that is commonly used now. Even our mobile phones use this technology as a security lock. Therefore, various algorithms continue to be developed to obtain maximum results with minimum costs. One of them is the Deep Neural Network or DNN algorithm. This DNN algorithm is part of the machine learning field. While DNN requires a large dataset to train the algorithm, another algorithm called the Principal Component Analysis (PCA) algorithm works good in a smaller dataset. These algorithms are compared to know which algorithm has the better result in given circumstances. Later the accuracy, speed, and optimality of the algorithms are analyzed. This project also examines the most preferable and optimum algorithms within the cases. By comparing these algorithms, we could know which algorithm is preferable based on your needs. First, fetch the Olivetti faces dataset with the help of the Sklearn dataset library and split the dataset into two parts; training set and testing set. Then, the DNN algorithm is trained using the training set. After that, the model trained is tested with the testing set. The same step is also done for the PCA algorithm. After the result is obtained, we can conclude which algorithm is better within the given condition. After the experiment is done, we can assume that the two algorithms have a s light difference in terms of accuracy. Also, the time used for running the PCA implementation code is slightly longer than DNN. However, that does not mean that the PCA algorithm is not great. If the dataset to be used is limited, PCA is going to be a good choice.

Item Type:	Thesis (Other)
Subjects:	000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions:	Faculty of Computer Science > Department of Informatics Engineering
Depositing User:	mr AM. Pudja Adjie Sudoso
Date Deposited:	23 Mar 2022 04:00
Last Modified:	23 Mar 2022 04:00
URI:	http://repository.unika.ac.id/id/eprint/28269

Actions (login required)

View Item